LLM Reference
Concepts & capability filters

Low-Rank Adaptation

LoRA (Low-Rank Adaptation) fine-tunes LLMs by freezing pre-trained weights and injecting trainable low-rank matrices into weight updates, approximating full fine-tuning with far fewer parameters.

Category
Not classified
Difficulty
Not classified
Aliases
None tracked
Last reviewed
2026-07-02

Key facts

  • It decomposes delta weights as low-rank matrices where rank r is much smaller than dimensions, enabling efficient task adaptation.

Models Mentioning Low-Rank Adaptation(2)